FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3171470186> ?p ?o ?g. }

• W3171470186 endingPage "663" @default.
• W3171470186 startingPage "653" @default.
• W3171470186 abstract "The process of diagnosis and survival rate along with endurance period is greatly decided by the type of cancer and the current existing stage of cancer disease. The information that is accurate could provide lots of help during patient treatment management and increase the chance of survival. The biopsy process through fine needle aspiration has generally been applied to rule out the presence of malignancy lesions. Cytologists analyzed the details and tried to establish the correlation among the various observations to deliver the outcome. The limitation of expertise and possibilities of natural human error can cause a significant impact on the diagnosis process as well as patient economical and cognition conditions. In this article, computational intelligence has developed over the neural network platform to predict the possibilities of lesions’ categorical belongings. The feed-forward architecture has considered developing the predictor because of its universal approximation quality. To obtain more robust outcomes in the decision instead of a single classifier, ensembles of classifiers have proposed where every individual classifier is having variability in the training data to avail the quality of knowledge diversity. The formation of weight-oriented ensemble has been done by evolutionary programming. It has been observed that the proposed method has delivered a high value of correct recognition in comparison to individual classifiers. The benefit of the proposed form of the ensemble has compared against conventional methods like majority voting and mean value decision. The strength of ensemble forming capability by evolutionary programming has compared with particle swarm optimization. The proposed ensemble benefit has further been tested over receiver operating characteristics environment to meet the practical challenges of variability in decision threshold value." @default.
• W3171470186 created "2021-06-22" @default.
• W3171470186 creator A5022137187 @default.
• W3171470186 creator A5024104784 @default.
• W3171470186 creator A5035031096 @default.
• W3171470186 date "2021-01-01" @default.
• W3171470186 modified "2023-10-03" @default.
• W3171470186 title "FNAB-Based Prediction of Breast Cancer Category Using Evolutionary Programming Neural Ensemble" @default.
• W3171470186 cites W1589262686 @default.
• W3171470186 cites W1915129189 @default.
• W3171470186 cites W2000000530 @default.
• W3171470186 cites W2090123125 @default.
• W3171470186 cites W2096023864 @default.
• W3171470186 cites W2253985880 @default.
• W3171470186 cites W2370924594 @default.
• W3171470186 cites W2415893778 @default.
• W3171470186 cites W2490276714 @default.
• W3171470186 cites W2530103281 @default.
• W3171470186 cites W2569219946 @default.
• W3171470186 cites W2594263488 @default.
• W3171470186 cites W2595298013 @default.
• W3171470186 cites W3046874697 @default.
• W3171470186 cites W58801888 @default.
• W3171470186 doi "https://doi.org/10.1007/978-981-33-6862-0_51" @default.
• W3171470186 hasPublicationYear "2021" @default.
• W3171470186 type Work @default.
• W3171470186 sameAs 3171470186 @default.
• W3171470186 citedByCount "1" @default.
• W3171470186 countsByYear W31714701862023 @default.
• W3171470186 crossrefType "book-chapter" @default.
• W3171470186 hasAuthorship W3171470186A5022137187 @default.
• W3171470186 hasAuthorship W3171470186A5024104784 @default.
• W3171470186 hasAuthorship W3171470186A5035031096 @default.
• W3171470186 hasConcept C110332635 @default.
• W3171470186 hasConcept C119857082 @default.
• W3171470186 hasConcept C119898033 @default.
• W3171470186 hasConcept C153180895 @default.
• W3171470186 hasConcept C154945302 @default.
• W3171470186 hasConcept C41008148 @default.
• W3171470186 hasConcept C45942800 @default.
• W3171470186 hasConcept C50644808 @default.
• W3171470186 hasConcept C5274069 @default.
• W3171470186 hasConcept C85617194 @default.
• W3171470186 hasConcept C95623464 @default.
• W3171470186 hasConceptScore W3171470186C110332635 @default.
• W3171470186 hasConceptScore W3171470186C119857082 @default.
• W3171470186 hasConceptScore W3171470186C119898033 @default.
• W3171470186 hasConceptScore W3171470186C153180895 @default.
• W3171470186 hasConceptScore W3171470186C154945302 @default.
• W3171470186 hasConceptScore W3171470186C41008148 @default.
• W3171470186 hasConceptScore W3171470186C45942800 @default.
• W3171470186 hasConceptScore W3171470186C50644808 @default.
• W3171470186 hasConceptScore W3171470186C5274069 @default.
• W3171470186 hasConceptScore W3171470186C85617194 @default.
• W3171470186 hasConceptScore W3171470186C95623464 @default.
• W3171470186 hasLocation W31714701861 @default.
• W3171470186 hasOpenAccess W3171470186 @default.
• W3171470186 hasPrimaryLocation W31714701861 @default.
• W3171470186 hasRelatedWork W3038539283 @default.
• W3171470186 hasRelatedWork W3136979370 @default.
• W3171470186 hasRelatedWork W3202701980 @default.
• W3171470186 hasRelatedWork W4224047587 @default.
• W3171470186 hasRelatedWork W4281560664 @default.
• W3171470186 hasRelatedWork W4285741730 @default.
• W3171470186 hasRelatedWork W4312206019 @default.
• W3171470186 hasRelatedWork W4312799535 @default.
• W3171470186 hasRelatedWork W4385189360 @default.
• W3171470186 hasRelatedWork W3214927170 @default.
• W3171470186 isParatext "false" @default.
• W3171470186 isRetracted "false" @default.
• W3171470186 magId "3171470186" @default.
• W3171470186 workType "book-chapter" @default.